Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 19764
    Prev
    Next
    INDEX
    Explanations

    phrases concerning the legal use and distribution of material

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to content usage restrictions and copyright

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mens
    -0.68
     Parables
    -0.61
    jen
    -0.59
    achine
    -0.59
    mons
    -0.57
     Carnage
    -0.56
    hers
    -0.55
    oad
    -0.54
    occ
    -0.53
     Hare
    -0.53
    POSITIVE LOGITS
     rewritten
    1.27
     archived
    0.90
     redistributed
    0.88
     reprinted
    0.78
     written
    0.75
     transmitted
    0.75
     reproduced
    0.74
    published
    0.74
     photographed
    0.74
     copied
    0.74
    Activations Density 0.044%

    No Known Activations